Obtenir les promotions Carrefour en cours pour une catégorie de produits.
AI agents call get_promotions to retrieve information from Mcp Carrefour without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and displays promotional data. It does not create, modify, delete, or execute any actions. It cannot move money, modify cart state, or trigger external operations. The blast radius of misuse is minimal—an agent could only retrieve promotional information repeatedly, which poses no security or operational risk.
From the tool's definition Tool description states 'Obtenir les promotions Carrefour en cours pour une catégorie de produits' (Get current Carrefour promotions for a product category). This is a data retrieval operation with no side effects.
Attacks that exploit this kind of access
Obtenir les promotions Carrefour en cours pour une catégorie de produits. It is categorised as a Read tool in the Mcp Carrefour MCP Server, which means it retrieves data without modifying state.
Register the Mcp Carrefour MCP server in PolicyLayer and add a rule for get_promotions: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Carrefour. Nothing to install.
get_promotions is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_promotions rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_promotions. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_promotions is provided by the Mcp Carrefour MCP server (nicovlr/mcp-carrefour). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →